US7346197B2 - Method of improving fingerprint images - Google Patents

Method of improving fingerprint images Download PDF

Info

Publication number
US7346197B2
US7346197B2 US10/512,868 US51286804A US7346197B2 US 7346197 B2 US7346197 B2 US 7346197B2 US 51286804 A US51286804 A US 51286804A US 7346197 B2 US7346197 B2 US 7346197B2
Authority
US
United States
Prior art keywords
grooves
image area
image
mean
spacing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US10/512,868
Other languages
English (en)
Other versions
US20050163394A1 (en
Inventor
Steffen Scholze
Alexander Schwarz
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
III Holdings 6 LLC
Original Assignee
NXP BV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NXP BV filed Critical NXP BV
Assigned to KONINKLIJKE PHILIPS ELECTRONICS N.V. reassignment KONINKLIJKE PHILIPS ELECTRONICS N.V. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: SCHOLZE, STEFFEN, SCHWARZ, ALEXANDER
Publication of US20050163394A1 publication Critical patent/US20050163394A1/en
Assigned to NXP B.V. reassignment NXP B.V. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: KONINKLIJKE PHILIPS ELECTRONICS N.V.
Application granted granted Critical
Publication of US7346197B2 publication Critical patent/US7346197B2/en
Assigned to III HOLDINGS 6, LLC reassignment III HOLDINGS 6, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: NXP B.V.
Assigned to NXP B.V. reassignment NXP B.V. RELEASE BY SECURED PARTY (SEE DOCUMENT FOR DETAILS). Assignors: MORGAN STANLEY SENIOR FUNDING, INC.
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—Preprocessing; Feature extraction

Definitions

  • the invention relates to a method of improving fingerprint images, wherein recorded images are processed on image areas of the fingerprint images by using Gabor filters.
  • Minutiae are branches and ends of individual grooves in the fingerprint.
  • the minutiae are extracted from a given fingerprint using known image processing methods. Errors in the production of fingerprint images hinder the detection of minutiae. Such errors can, for example, arise from different composition of the finger surface at the time of photographing, for example, sweat, dirt, dryness and the like.
  • U.S. Pat. No. 5,659,626 discloses a fingerprint identification system in which processing is performed in accordance with the type of the main claim using Gabor filters. Gabor filters are described further in Lin Hong, Yifei Wan, and Anil Jain: “Fingerprint Image Enhancement: Algorithm and Performance Evaluation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20. 8, Aug. 1998.
  • the Gabor filters are adapted to characteristic quantities of the image in the relevant image area to be processed.
  • the method according to the invention is preferably characterized in that the image areas are square and have a side length at which the spacing and direction changes of the grooves are relatively small but comprise several grooves, such that statistical mean values and the standard deviations can be formed for the spacings and directions.
  • FIG. 1 a and FIG. 1 b show fingerprint images before and after processing by means of the method according to the invention with the result of an improved groove contour
  • FIG. 2 a and FIG. 2 b show fingerprint images before and after processing by means of the method according to the invention with the result of an improved groove separation
  • FIG. 4 a and FIG. 4 b show views to explain the combining of tiles
  • FIG. 5 shows a plan view of the FFT-transform of a square quadratic image area.
  • FIGS. 1 and 2 Because of the specifications for patent drawings which state that the figures must not contain gray shades, the fingerprint images in FIGS. 1 and 2 are shown largely as pure black/white images.
  • a corresponding computer program can be run on a computer.
  • the calculation of local gradients G is performed on a suitable grid of, for example, 8 ⁇ 8 pixels.
  • local groove spacings R are also calculated on the suitable grid.
  • the fingerprint image is divided into tiles K of suitable size.
  • a suitable size is, for example, 32 ⁇ 32 pixels for a sensor-induced image resolution of 500 dpi.
  • a counter c is initialized, i.e. set to zero.
  • parameters are calculated for construction of the Gabor filter according to the characteristic quantities.
  • mean is the mean value and std is the standard deviation.
  • the Gabor filter GF for the tile K(c) is constructed as a function of the parameters calculated in 8 .
  • FIG. 4 shows a tile K(c), and in dotted lines, the adjacent tiles which each overlap.
  • FIG. 4 b shows an example of a weighting function W as a function of distance x. Whereas in the central area of the tiles a maximum weighting is applied, this diminishes in the overlap areas up to the edges.
  • the center point of the ellipse describes the maximum of the bell curve and lies precisely at the intersection of frequency and direction.
  • the frequency space is viewed as follows: The origin lies in the center of the Gabor filter and can be described with the amplitude of the equal part. Concentric circles about the origin (0,0) contain the same frequency in different directions, where the frequency is limited at the outer edge by the FFT-specific limit frequency. In this simplified view, the imaginary part of both the transform and the inverse transform is disregarded. Thus, the frequency space can be regarded as the polar co-ordinate representation of frequency and direction.
  • the implementation has size 32 ⁇ 32 for the square FFT/IFFT tiles K.
  • the Gabor filter in the frequency area is formed pixel by pixel for:
  • v ( x y ) - 1 mR ⁇ ( cos ⁇ ⁇ m ⁇ ⁇ G sin ⁇ ⁇ m ⁇ ⁇ G ) , where mR is the mean groove spacing and mG is the mean direction of the groove to the inner part of the tile being processed, calculated, for example, by means of
  • mR 1 # ⁇ ⁇ M ⁇ ⁇ ⁇ m 1 , m 2 ⁇ M ⁇ R ⁇ ( x + m 1 , y + m 2 ) [ 2 ]
  • M is the quantity of elements of R existing on the tile.
  • mR R ⁇ ( x + 12 , y + 12 ) + R ⁇ ( x + 12 , y + 20 ) + R ⁇ ( x + 20 , y + 12 ) + R ⁇ ( x + 20 , y + 20 ) 4 [ 3 ] with (x,y) as co-ordinates of the top left-hand corner of the tile processed in each case.
  • the value mG can be taken e.g. directly from a suitably smoothed grid of directions, as the innermost grid point of G in the tile being processed. This can be performed instead of the mean value formation and is possible because of the previously performed smoothing of the direction grid and prevents a complex mean value formation of the directions.
  • Matrix A in [1] is derived from

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Collating Specific Patterns (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
US10/512,868 2002-03-20 2003-03-17 Method of improving fingerprint images Active 2024-12-21 US7346197B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
DE10212277A DE10212277A1 (de) 2002-03-20 2002-03-20 Verfahren zur Verbesserung von Fingerabdruck-Bildern
DE10212277.6 2002-03-20
PCT/IB2003/000951 WO2003079274A1 (en) 2002-03-20 2003-03-17 Method of improving fingerprint images

Publications (2)

Publication Number Publication Date
US20050163394A1 US20050163394A1 (en) 2005-07-28
US7346197B2 true US7346197B2 (en) 2008-03-18

Family

ID=27797952

Family Applications (1)

Application Number Title Priority Date Filing Date
US10/512,868 Active 2024-12-21 US7346197B2 (en) 2002-03-20 2003-03-17 Method of improving fingerprint images

Country Status (7)

Country Link
US (1) US7346197B2 (de)
EP (1) EP1488370B1 (de)
JP (1) JP2005521137A (de)
AT (1) ATE404937T1 (de)
AU (1) AU2003209568A1 (de)
DE (2) DE10212277A1 (de)
WO (1) WO2003079274A1 (de)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11170513B2 (en) 2016-01-07 2021-11-09 Rapsodo Pte. Ltd. Object surface matching with a template for flight parameter measurement

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10212277A1 (de) * 2002-03-20 2003-10-02 Philips Intellectual Property Verfahren zur Verbesserung von Fingerabdruck-Bildern
CN100357956C (zh) * 2003-01-09 2007-12-26 Nxp股份有限公司 二值化含有线性结构的图像的方法
WO2004079637A1 (es) * 2003-03-07 2004-09-16 Consejo Superior De Investigaciones Científicas Procedimiento para el reconocimiento de patrones en imagenes afectadas por degradaciones ôpticas y su aplicaciôn a la predicciôn de la agudeza visual a partir de datos de aberrometria ocular del paciente
FR2865057B1 (fr) * 2004-01-09 2006-06-16 Zefyr Trechnologies Procede d'amelioration d'images d'empreintes digitales
RU2329537C1 (ru) 2006-11-08 2008-07-20 Владимир Николаевич Бичигов Способ фильтрации дактилоскопического изображения
EA200900144A1 (ru) * 2008-12-19 2009-12-30 Владимир Николаевич Бичигов Способ оценки качества изображения дактилоскопического узора
US8184294B2 (en) * 2009-03-09 2012-05-22 Honeywell International Inc. Apparatus and method for measuring haze of sheet materials or other materials
SE1551643A1 (en) * 2015-12-14 2017-06-15 Fingerprint Cards Ab Method and fingerprint sensing system for forming a fingerprint image
US11080546B2 (en) 2017-10-13 2021-08-03 Fingerprint Cards Ab Method and system for fingerprint image enhancement
US20230119918A1 (en) * 2021-10-14 2023-04-20 Thales Dis France Sas Deep learning based fingerprint minutiae extraction

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5659626A (en) * 1994-10-20 1997-08-19 Calspan Corporation Fingerprint identification system
US20050163394A1 (en) * 2002-03-20 2005-07-28 Steffen Scholze Method of improving fingerprint images
US20050232472A1 (en) * 2002-08-28 2005-10-20 Koninklijke Philips Electronics N.V. Method and apparatus of processing a skin print image
US20060210123A1 (en) * 2001-02-28 2006-09-21 Matsushita Electric Industrial Co., Ltd. Personal authentication method and device
US7142699B2 (en) * 2001-12-14 2006-11-28 Siemens Corporate Research, Inc. Fingerprint matching using ridge feature maps

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5659626A (en) * 1994-10-20 1997-08-19 Calspan Corporation Fingerprint identification system
US5799098A (en) * 1994-10-20 1998-08-25 Calspan Corporation Fingerprint identification system
US5926555A (en) * 1994-10-20 1999-07-20 Calspan Corporation Fingerprint identification system
US20060210123A1 (en) * 2001-02-28 2006-09-21 Matsushita Electric Industrial Co., Ltd. Personal authentication method and device
US7142699B2 (en) * 2001-12-14 2006-11-28 Siemens Corporate Research, Inc. Fingerprint matching using ridge feature maps
US20050163394A1 (en) * 2002-03-20 2005-07-28 Steffen Scholze Method of improving fingerprint images
US20050232472A1 (en) * 2002-08-28 2005-10-20 Koninklijke Philips Electronics N.V. Method and apparatus of processing a skin print image

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Greenberg S, et al: "Fingerprint Image Enhancement Using Filtering Techniques" Pattern Recognition, 2000. Proceedinds, 15<SUP>TH </SUP>International Conference on Sep. 3-7, 2000, IEEE Comput. Soc., US, Sep. 3, 2000.
Hong, L. et al: "Fingerprint Image Enhancement: Algorithm and Performance Evaluation" IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Inc. New York, US vol. 20, No. 8, Aug. 1, 1998, pp. 777-789.
Jiang, X: " A Study of Fingerprint Image Filtering" Proceedings 2001 International Conference on Image Processing. ICIP 2001. Thessaloniki, Greece, Oct. 7-10, 2001, IEEE, vol. 3 of 3, Conf. 8, Oct. 7, 2001.

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11170513B2 (en) 2016-01-07 2021-11-09 Rapsodo Pte. Ltd. Object surface matching with a template for flight parameter measurement

Also Published As

Publication number Publication date
DE60322855D1 (de) 2008-09-25
EP1488370A1 (de) 2004-12-22
US20050163394A1 (en) 2005-07-28
AU2003209568A1 (en) 2003-09-29
DE10212277A1 (de) 2003-10-02
EP1488370B1 (de) 2008-08-13
WO2003079274A1 (en) 2003-09-25
JP2005521137A (ja) 2005-07-14
ATE404937T1 (de) 2008-08-15

Similar Documents

Publication Publication Date Title
JP2776294B2 (ja) 皮膚紋様画像の画像特徴抽出装置および画像処理装置
US7346197B2 (en) Method of improving fingerprint images
US8306288B2 (en) Automatic identification of fingerprint inpainting target areas
US20030169910A1 (en) Fingerprint matching using ridge feature maps
US10776953B2 (en) Method for identification of candidate points as possible characteristic points of a calibration pattern within an image of the calibration pattern
US7072523B2 (en) System and method for fingerprint image enhancement using partitioned least-squared filters
CN102930241B (zh) 指纹图像的处理方法和处理装置
CN109919960B (zh) 一种基于多尺度Gabor滤波器的图像连续边缘检测方法
CN101329726B (zh) 一种基于一维滤波的指纹图像增强方法
WO2020155764A1 (zh) 掌纹提取方法、装置及存储介质、服务器
US7466846B2 (en) Method for analyzing a palm print for the identification of an individual using gabor analysis
US8526687B2 (en) Method for filtering a fingerprint image continuation-in-part
Ahmed et al. Fingerprint image enhancement based on threshold fast discrete curvelet transform (FDCT) and gabor filters
Jirachaweng et al. Fingerprint enhancement based on discrete cosine transform
Kekre et al. Fingerprint core point detection algorithm using orientation field based multiple features
US7502524B2 (en) Method and apparatus of processing a skin print image
JP4020202B2 (ja) 縞状パターン抽出システムおよび縞状パターン抽出方法
CN111160290B (zh) 一种提取手掌静脉有效区域的方法
Cheng The distinctiveness of a curve in a parameterized neighborhood: extraction and applications
Fahmy et al. A novel scheme for fingerprint enhancement
Quadri et al. Performance analysis and designing of fingerprints enhancement technique based on segmentation, of estimation and ridge frequency, gabor filters with wavelet transform
JP3816826B2 (ja) 市街地領域抽出処理方法，市街地領域抽出処理装置，市街地領域抽出処理プログラムおよびそのプログラムの記録媒体
RU2364936C1 (ru) Способ формирования представления (шаблона) отпечатка пальца человека
EP1586072B1 (de) Verfahren zur binärisierung von linearestrukturen enthaltenden bildern
Hashmi et al. Fuzzy based image forensic tool for detection and classification of image cloning

Legal Events

Date Code Title Description
AS Assignment

Owner name: KONINKLIJKE PHILIPS ELECTRONICS N.V., NETHERLANDS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SCHOLZE, STEFFEN;SCHWARZ, ALEXANDER;REEL/FRAME:016311/0912

Effective date: 20030310

AS Assignment

Owner name: NXP B.V., NETHERLANDS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:KONINKLIJKE PHILIPS ELECTRONICS N.V.;REEL/FRAME:019719/0843

Effective date: 20070704

Owner name: NXP B.V.,NETHERLANDS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:KONINKLIJKE PHILIPS ELECTRONICS N.V.;REEL/FRAME:019719/0843

Effective date: 20070704

STCF Information on status: patent grant

Free format text: PATENTED CASE

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

AS Assignment

Owner name: III HOLDINGS 6, LLC, DELAWARE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:NXP B.V.;REEL/FRAME:036304/0330

Effective date: 20150730

AS Assignment

Owner name: NXP B.V., NETHERLANDS

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC.;REEL/FRAME:037614/0856

Effective date: 20150529

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 12